Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to actions involving assistance or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following prepositions and pronouns

    np_acts-logits-general · gemini-2.0-flash

    preposition followed by pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doubtnut
    -0.70
    $")
    -0.66
     preſent
    -0.64
    bagai
    -0.64
    bleau
    -0.63
     ſeveral
    -0.63
    Попис
    -0.62
    sterious
    -0.62
    AutoScaleMode
    -0.61
     SIMBAD
    -0.61
    POSITIVE LOGITS
     him
    2.01
     them
    1.98
     us
    1.87
     me
    1.71
    them
    1.33
    him
    1.13
     you
    1.10
     eux
    1.03
     THEM
    1.00
     ellos
    0.95
    Act Density 0.461%

    No Known Activations